Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 663 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2604. Min Range: -5.2604
Max Act: 5.2604. Min Act: -0.1700
Data Index: 8713953 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2604. Min Range: -5.2604
Max Act: 5.2292. Min Act: -0.1700
Data Index: 7958085 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2604. Min Range: -5.2604
Max Act: 5.1042. Min Act: -0.1700
Data Index: 900404 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2604. Min Range: -5.2604
Max Act: 5.0729. Min Act: -0.1700
Data Index: 3485025 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2604. Min Range: -5.2604
Max Act: 5.0417. Min Act: -0.1700
Data Index: 6109448 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.9792. Min Act: -0.1700
Data Index: 7019537 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.9167. Min Act: -0.1700
Data Index: 5143359 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.8854. Min Act: -0.1700
Data Index: 8245572 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.8542. Min Act: -0.1700
Data Index: 7457878 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.8542. Min Act: -0.1700
Data Index: 6241792 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.8229. Min Act: -0.1700
Data Index: 1641605 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 4742762 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 4156942 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 2450220 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 259037 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7292. Min Act: -0.1700
Data Index: 5480452 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 3394265 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7604. Min Act: -0.1700
Data Index: 908784 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7917. Min Act: -0.1700
Data Index: 7280431 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2604. Min Range: -5.2604
Max Act: 4.7292. Min Act: -0.1700
Data Index: 3806678 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19